http://repositorio.ufc.br/handle/riufc/484 2026-04-08T09:19:24Z http://repositorio.ufc.br/handle/riufc/85335 Título: SenseAir: arquitetura de monitoramento de qualidade do ar com sensores de baixo custo e visão computacional para tráfego veicular Autor(es): Monteiro, Nícolas de Carvalho Abstract: The scarcity and regional concentration of reference air quality monitoring stations in Brazil limit reliable diagnostics and the design of evidence-based public policies, especially in undermonitored regions such as the Northeast. As a complementary alternative to official networks, this dissertation investigates a low-cost architecture composed of an embedded sensor node (SenseAir), a real-time mobile application, a computer vision model for vehicle traffic quantification, and an exploratory calibration module for PM2,5 anchored in data from a higher-performance portable instrument. The solution integrates continuous data acquisition, secure transmission and cloud storage, and visualization of the Air Quality Index (AQI) derived from PM2,5 with geolocation, targeting indicative monitoring in urban scenarios. Calibration is discussed in light of U.S. EPA guidelines for PM2,5 sensors, using metrics such as coefficient of determination (R2), bias (regression slope and intercept), and root mean square error (RMSE) to evaluate the correction applied to SenseAir. In parallel, a YOLO-based model embedded in the Raspberry Pi estimates the flow and composition of the vehicle fleet, enabling analysis of the role of traffic, together with other external factors, in the local degradation of air quality. The results discuss cost, performance, and limitations of the proposed architecture, as well as its potential use in dense indicative monitoring networks and in research and decision-support applications for public management. Tipo: Dissertação 2026-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/84810 Título: Aplicação da função de Lambert-Tsallis na solução de um circuito resistor-capacitor com decaimento não exponencial Autor(es): Ramos, Lucio André Bastos Abstract: The present dissertation uses the Lambert-Tsallis Wq function in order to get the analytical solution for the non-exponential decay of the total electric current in an electric circuit, fed with a DC power supply, composed by two parallel branches of resistor-capacitor series circuits. The result obtained permits the analytical calculation of the half-life time of the total electrical current, that is, the time required for the total current to decay to half of its initial value. Following, it was shown that the solution for the half-life time of the total electrical current obeys a Fermat-type equation therefore, depending on the values chosen for the resistors and capacitors be algebraic or transcendental numbers, integers value larger than two for the half-life time can be forbidden or not. This is a physical example of the famous Fermat last theorem from number theory, as well it demonstrates a physical implication of the usage of algebraic and transcendental numbers. At last, it was presented the electronic circuit of an oscillator, named Fermat’s oscillator, whose oscillation period depends on the solution of the Fermat equation. Tipo: Dissertação 2025-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/84629 Título: A new methodology for edge intelligence data quality evaluation in IDD abd Non-IID datasets in federated learning Autor(es): Valente Neto, Ernesto Gurgel Abstract: Massive data generation from Internet of Things (IoT) devices increases the demand for efficient data analysis to extract meaningful insights. Federated Learning (FL) allows IoT devices to collaborate in Artificial Intelligence (AI) training models while preserving data privacy. However, selecting high-quality data for training remains a critical challenge in FL environments with non-independent and identically distributed (non-iid) data. Poor-quality data introduce errors, delay convergence, and increase computational costs. This study develops a data quality analysis algorithm for FL and centralized environments to address these challenges. The proposed algorithm reduces computational costs, eliminates unnecessary data processing, and accelerates AI model convergence. The experiments used the MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets, and performance evaluation was based on main literature metrics like accuracy, recall, F1 score, and precision. Results show the best-case execution time reductions of up to 56.49%, with an accuracy loss of around 0.50%. Tipo: Dissertação 2025-01-01T00:00:00Z http://repositorio.ufc.br/handle/riufc/82761 Título: Aplicação de sensores de baixo custo no suporte a tomada de decisão em irrigação de precisão Autor(es): Sousa, Otto Álan Pinto de Abstract: Food production plays a fundamental role in developing a fairer world, which is essential for food security and human well-being. As one of the pillars of this production, agriculture has faced increasing challenges due to water scarcity, a vital resource directly responsible for plant health and productive performance. Water stress in plants, characterized by the lack of water in the soil, can be aggravated by adverse weather conditions or inadequate agricultural practices, such as insufficient irrigation. Although there are consolidated techniques for detecting water stress, most of these are expensive and operationally complex, which makes their adoption difficult for small and medium-sized producers. In this context, this work proposes developing a low-cost system using Internet of Things technologies for monitoring plant water stress, using leaf temperature as an indicator. Under normal conditions, transpiration keeps leaf temperature below that of the air, while in water stress, the lack of transpiration raises leaf temperature above the air temperature. The proposal was validated in an experimental corn plantation of the BRS-Gorotuba cultivar and two sorghum cultivars (the first tolerant and the second sensitive to water deficit), in which the results obtained, based on the physiological response of the plants and the collection of air temperature through aspirated psychrometers, demonstrated the effectiveness of the developed system. In addition, the analysis of the collected data highlights the tool's potential to improve precision irrigation practices, enabling more efficient management of water resources and, consequently, contributing to the sustainability of agricultural production. Tipo: Dissertação 2025-01-01T00:00:00Z